Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176531,
        author = {Aditya Suryawanshi and Shardul Deshmukh and Sujal Pore and Disha Nagpure},
        title = {Multi Model RAG Application: AI Observability & Document Intelligence},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {5848-5856},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176531},
        abstract = {This paper presents SASAi and Studently.ai, two integrated multimodal chatbot platforms designed to address the growing need for intelligent, real-time document summarization and AI observability. Leveraging state-of-the-art Retrieval-Augmented Generation (RAG) architectures, the systems utilize generative models such as OpenAI’s GPT and Google’s Gemini, along with orchestration frameworks like LangChain and CrewAI. The proposed solution focuses on streamlining tasks such as resume parsing and YouTube video summarization—domains where traditional tools fall short in handling unstructured multimodal data effectively. SASAi incorporates a robust observability layer powered by Arize Phoenix, enabling end-to-end monitoring, traceability, and performance evaluation of generative agents in production. Built with scalable deployment in mind, both systems support diverse input formats including text, images, PDFs, and URLs, while offering seamless integration into web-based environments using Vercel, Streamlit, and Python-based tools. Evaluation results demonstrate reduced latency, improved contextual accuracy, and enhanced system transparency. This work serves as a second installment in our research, extending previous findings by introducing enhanced observability and multi-agent task coordination in a multimodal context. The platform highlights the importance of blending GenAI with monitoring pipelines to ensure responsible, adaptive AI in real-world applications.},
        keywords = {Multimodal RAG, AI Chatbot, Observability, Document Intelligence, Generative AI, LangChain},
        month = {May},
        }